I am a PhD student at Yale working with Professor Tom McCoy. My current research interests are in interpreting and evaluating neural networks as models of language/cognition. I believe that this line of work can (1) on the theoretical side, shed light on the nature of both natural and artificial intelligence, and (2) on the practical side, help build better AI systems. Much this is also fueled by my interest in analytic philosophy, especially philosophy of language.
Before Yale, I was at Brown where I did applied math-computer science and engineering. Before Brown, I was a mechanical engineering and statistics double major at Rutgers University (from which I transferred). And even before that, I spent two years by the Bristol Channel at UWC Atlantic.
Besides academic stuff, I enjoy cycling and kendo. I also listen to JPop.
I’m happy to talk about research as well as my interests/experiences in general. Feel free to shoot me an email at !
Note: My name is written as Zhang Enyan for academic work. Part of the reason is that this is how it appears in Chinese (family name first), but also that unlike most European languages, Chinese given names are unique, while last names are widely shared and not very indicative of family heritage (e.g. there are roughly 87 million people with my last name in mainland China).
Publications
{Author A, Author B} indicates equal contribution.
Are LLMs Models of Distributional Semantics? A Case Study on Quantifiers{Zhang Enyan, Zewei Wang}, Michael A. Lepori, Ellie Pavlick, Helena Aparicio
Under Review
[arXiv]
Zhang Enyan, Michael A. Lepori, Ellie Pavlick
Under Review
[arXiv, code]
